
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import folium
import glob
import warnings
warnings.simplefilter(action='ignore', category=FutureWarning)
%matplotlib inline


files = glob.glob("data/*.csv")
frames=[]
for file in files:
    frames.append(pd.read_csv(file, index_col=None, header=0))

/home/abdulrahman/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3146: DtypeWarning: Columns (14) have mixed types.Specify dtype option on import or set low_memory=False.
  has_raised = await self.run_ast_nodes(code_ast.body, cell_name,
/home/abdulrahman/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3146: DtypeWarning: Columns (13,14) have mixed types.Specify dtype option on import or set low_memory=False.
  has_raised = await self.run_ast_nodes(code_ast.body, cell_name,
/home/abdulrahman/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3146: DtypeWarning: Columns (13) have mixed types.Specify dtype option on import or set low_memory=False.
  has_raised = await self.run_ast_nodes(code_ast.body, cell_name,


df = pd.concat(frames, axis=0, ignore_index=True)


# save new dataset
df.to_csv('bike.csv', index=False)


df = pd.read_csv('bike.csv')


df.head()


df.sample(5)


# Info about the dataset
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2506983 entries, 0 to 2506982
Data columns (total 15 columns):
 #   Column                   Dtype  
---  ------                   -----  
 0   duration_sec             int64  
 1   start_time               object 
 2   end_time                 object 
 3   start_station_id         float64
 4   start_station_name       object 
 5   start_station_latitude   float64
 6   start_station_longitude  float64
 7   end_station_id           float64
 8   end_station_name         object 
 9   end_station_latitude     float64
 10  end_station_longitude    float64
 11  bike_id                  int64  
 12  user_type                object 
 13  bike_share_for_all_trip  object 
 14  rental_access_method     object 
dtypes: float64(6), int64(2), object(7)
memory usage: 286.9+ MB


# more information about the dataset
df.describe().transpose()


# check Null/Nan Values
missing_values = df.isna().sum()
df.isna().sum()

duration_sec                     0
start_time                       0
end_time                         0
start_station_id             80734
start_station_name           80133
start_station_latitude           0
start_station_longitude          0
end_station_id               82902
end_station_name             82350
end_station_latitude             0
end_station_longitude            0
bike_id                          0
user_type                        0
bike_share_for_all_trip     243259
rental_access_method       2386145
dtype: int64


# Check for duplicates
df[df.duplicated()==True]


df.drop('rental_access_method', axis=1, inplace=True)
df.sample(5)


# missing values is small percentage of total data, so I will drop it
df.dropna(inplace=True)


df.isna().sum()

duration_sec               0
start_time                 0
end_time                   0
start_station_id           0
start_station_name         0
start_station_latitude     0
start_station_longitude    0
end_station_id             0
end_station_name           0
end_station_latitude       0
end_station_longitude      0
bike_id                    0
user_type                  0
bike_share_for_all_trip    0
dtype: int64


df.sample(5)


df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 2262979 entries, 0 to 2355470
Data columns (total 14 columns):
 #   Column                   Dtype  
---  ------                   -----  
 0   duration_sec             int64  
 1   start_time               object 
 2   end_time                 object 
 3   start_station_id         float64
 4   start_station_name       object 
 5   start_station_latitude   float64
 6   start_station_longitude  float64
 7   end_station_id           float64
 8   end_station_name         object 
 9   end_station_latitude     float64
 10  end_station_longitude    float64
 11  bike_id                  int64  
 12  user_type                object 
 13  bike_share_for_all_trip  object 
dtypes: float64(6), int64(2), object(6)
memory usage: 259.0+ MB


# change to datetime format
df.start_time = pd.to_datetime(df.start_time)
df.end_time = pd.to_datetime(df.end_time)


# insert new columns
df.insert(0, 'duration_mins', (df.duration_sec/60))
df.insert(1, 'start_day', (df.start_time.dt.strftime('%a')))
df.insert(2, 'end_day', (df.end_time.dt.strftime('%a')))
df.insert(3, 'start_month', (df.start_time.dt.strftime('%b')))
df.insert(4, 'end_month', (df.end_time.dt.strftime('%b')))
df.insert(5, 'start_hour', (df.start_time.dt.hour))
df.insert(6, 'end_hour', (df.end_time.dt.hour))


df.head()


# calculate the distance in miles between start and end stations
df['distance_miles'] = 3958.756 * 2 * np.arcsin(np.sqrt(np.sin((np.radians(df['end_station_latitude']) - \
                    np.radians(df['start_station_latitude']))/2)**2 + np.cos(np.radians(df['start_station_latitude'])) * \
                    np.cos(np.radians(df['end_station_latitude'])) * np.sin((np.radians(df['end_station_longitude']) - \
                    np.radians(df['start_station_longitude']))/2)**2))


df.sample(5)


df.bike_id = df.bike_id.astype(str)
df.start_station_id = df.start_station_id.astype(str)
df.end_station_id = df.end_station_id.astype(str)
df.duration_mins = df.duration_mins.round()
df.duration_mins = df.duration_mins.astype(np.int64)
df.user_type = df.user_type.astype('category')


df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 2262979 entries, 0 to 2355470
Data columns (total 22 columns):
 #   Column                   Dtype         
---  ------                   -----         
 0   duration_mins            int64         
 1   start_day                object        
 2   end_day                  object        
 3   start_month              object        
 4   end_month                object        
 5   start_hour               int64         
 6   end_hour                 int64         
 7   duration_sec             int64         
 8   start_time               datetime64[ns]
 9   end_time                 datetime64[ns]
 10  start_station_id         object        
 11  start_station_name       object        
 12  start_station_latitude   float64       
 13  start_station_longitude  float64       
 14  end_station_id           object        
 15  end_station_name         object        
 16  end_station_latitude     float64       
 17  end_station_longitude    float64       
 18  bike_id                  object        
 19  user_type                category      
 20  bike_share_for_all_trip  object        
 21  distance_miles           float64       
dtypes: category(1), datetime64[ns](2), float64(5), int64(4), object(10)
memory usage: 382.0+ MB


# drop unwanted columns
def drop_cols(df, cols_list):
    """ Drop cols form dataframe
    """
    for col in cols_list:
        df.drop(col, axis=1, inplace=True)

drop_cols(df, ['start_time', 'end_time', 'duration_sec'])


df.sample(5)


# change seaborn style
sns.set_style('darkgrid')


fig, ax = plt.subplots(nrows=2, figsize = [12, 6])
ax[0].hist(data = df, x='duration_mins', bins=np.arange(0, df.duration_mins.mean()+40, 1), color='b', alpha=0.8, edgecolor='k')
ax[1].hist(data = df, x = 'duration_mins', bins=10 ** np.arange(0, 2.0, 0.09), color='b', alpha=0.8, edgecolor='k')
plt.xscale('log')
plt.sca(ax[0])
plt.xticks(np.arange(0, 55, 1))
plt.title("Rental duration in minutes - Normal Scale", fontsize=16)
plt.ylim(0, 180000)
plt.xlabel("Rental duration in minutes", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.sca(ax[1])
plt.title("Rental duration in minutes - Log Scale", fontsize=16)
plt.xlabel("Rental duration in minutes - Log x scale", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.tight_layout()
plt.show()


sns.countplot(data = df, x = 'user_type', color='b')
sns.set(rc={'figure.figsize':(12, 6)})
plt.title("Number of Subscribers vs Customers", fontsize=16)
plt.xlabel("User Type", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.show()


sub_count = df.user_type.value_counts()[0]
cust_count = df.user_type.value_counts()[1]
total = sub_count+cust_count
plt.pie([sub_count/total*100, cust_count/total*100], autopct='%1.1f%%', labels = ['Subscribers', 'Customers'], startangle=90)
plt.title('Percentage of Subscribers vs Customers', fontsize=16)
plt.axis('equal')
plt.show()


# days of week and months in the dataframe
days, months = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'], df.start_month.unique()


# Distribution of rentals across days of the week, months and hour
fig, ax = plt.subplots(nrows=3, figsize = [14, 8])
sns.countplot(data = df, x = 'start_hour', color = 'b', alpha=0.8, ax = ax[0])
plt.sca(ax[0])
plt.title("Number Of Rentals vs Hour", fontsize=16)
plt.xlabel("Start Hour", fontsize=16)
plt.ylabel("Count", fontsize=16)
sns.countplot(data = df, x = 'start_day', color = 'b', alpha=0.8, ax = ax[1], order=days)
plt.sca(ax[1])
plt.title("Number Of Rentals vs Day", fontsize=16)
plt.xlabel("Start Day", fontsize=16)
plt.ylabel("Count", fontsize=16)
sns.countplot(data = df, x = 'start_month', color = 'b', alpha=0.8, ax = ax[2])
plt.sca(ax[2])
plt.title("Number Of Rentals vs Month", fontsize=16)
plt.xlabel("Start Month", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.tight_layout()
plt.show()


# count subscribers in bike share for all scheme
sns.countplot(df[df.user_type == 'Subscriber'].bike_share_for_all_trip)
plt.title("Subscribers in Bike Share for All scheme", fontsize=16)
plt.show()

/home/abdulrahman/anaconda3/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(


# percentage of subscribers in bike share for all scheme
no_count = df.bike_share_for_all_trip.value_counts()[0]
yes_count = df.bike_share_for_all_trip.value_counts()[1]
plt.pie([no_count/(no_count+yes_count)*100, yes_count/(no_count+yes_count)*100], autopct='%1.1f%%', labels=['No', 'Yes'], startangle=90)
plt.title("Percentage of Subscribers in Bike Share for All scheme", fontsize=15)
plt.axis('equal')
plt.show()


# calc total distance of both subscribers and customers and their summation 
sub_dist = df[df.user_type == 'Subscriber'].distance_miles.sum()
cust_dist = df[df.user_type == 'Customer'].distance_miles.sum()
tot_dist = df.distance_miles.sum()


# percentage of subscribers in bike share for all scheme
plt.pie([sub_dist/tot_dist*100, cust_dist/tot_dist*100], autopct='%1.1f%%', labels=['Subscribers', 'Customers'], startangle=90)
plt.title("Distance travelled", fontsize=16)
plt.axis('equal')
plt.show()


# calc total duration of both subscribers and customers and their summation 
sub_dur = df[df.user_type == 'Subscriber'].duration_mins.sum()
cust_dur = df[df.user_type == 'Customer'].duration_mins.sum()
tot_dur = df.distance_miles.sum()


# calc duration percentage of both subscribers and customers 
plt.pie([sub_dur/tot_dur*100, cust_dur/tot_dur*100], autopct='%1.1f%%', labels=['Subscribers', 'Customers'], startangle=90)
plt.axis('equal')
plt.title('Rental duration of Subscribers and Customers', fontsize=15)
plt.show()


# duration in minutes traveled by subscribers
fig, ax = plt.subplots(nrows=2, figsize = [12, 5])
sub = df[df.user_type=='Subscriber']
ax[0].hist(sub.duration_mins, bins=np.arange(0, 40, 1), color='b', alpha=0.8, edgecolor='k')
ax[1].hist(sub.duration_mins, bins=10 ** np.arange(0, 2, 0.08), color='b', alpha=0.8, edgecolor='k')
plt.xscale('log')
plt.sca(ax[0])
plt.xticks(np.arange(0, 40, 1))
plt.title("Rental duration for subscribers in minutes - Normal Scale", fontsize=16)
plt.xlabel("Rental duration for subscribers in minutes", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.sca(ax[1])
plt.title("Rental duration for subscribers in minutes - Log Scale", fontsize=16)
plt.xlabel("Rental duration for subscribers in minutes", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.tight_layout()
plt.show()


# duration in minutes traveled by customers
fig, ax = plt.subplots(nrows=2, figsize = [12, 5])
sub = df[df.user_type=='Customer']
ax[0].hist(sub.duration_mins, bins=np.arange(0, 40, 1), color='b', alpha=0.8, edgecolor='k')
ax[1].hist(sub.duration_mins, bins=10 ** np.arange(0, 2, 0.08), color='b', alpha=0.8, edgecolor='k')
plt.xscale('log')
plt.sca(ax[0])
plt.xticks(np.arange(0, 40, 1))
plt.yticks(np.arange(0, 18000, 4000))
plt.title("Rental duration for customers in minutes - Normal Scale", fontsize=16)
plt.xlabel("Rental duration for customers in minutes", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.sca(ax[1])
plt.title("Rental duration for customers in minutes - Log Scale", fontsize=16)
plt.xlabel("Rental duration for customers in minutes", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.tight_layout()
plt.show()


# duration in minutes traveled by all trip program
fig, ax = plt.subplots(nrows=2, figsize = [12, 5])
sub = df[df.bike_share_for_all_trip=='Yes']
ax[0].hist(sub.duration_mins, bins=np.arange(0, 40, 1), color='b', alpha=0.8, edgecolor='k')
plt.sca(ax[0])
plt.xticks(np.arange(0, 40, 1))
plt.title("Rental duration for all users in minutes - Normal Scale", fontsize=16)
plt.xlabel("Rental duration for all users in minutes", fontsize=16)
plt.ylabel("Count", fontsize=16)
ax[1].hist(sub.duration_mins, bins=10 ** np.arange(0, 2, 0.08), color='b', alpha=0.8, edgecolor='k')
plt.sca(ax[1])
plt.xscale('log')
plt.title("Rental duration for all users in minutes - Log Scale", fontsize=16)
plt.xlabel("Rental duration for all users in minutes", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.tight_layout()
plt.show()


# distance in miles traveled by all types of users
fig, ax = plt.subplots(nrows=3, figsize = [16, 10])
sub = df[df.user_type=='Subscriber']
bins = np.arange(0, 3.5, 0.05)
ax[0].hist(sub.distance_miles, bins=bins, color='b', alpha=0.8, edgecolor='k')
plt.sca(ax[0])
plt.xticks(np.arange(0, 4, 0.1))
plt.title("Subscribers", fontsize=16)
plt.xlabel("Distance in miles", fontsize=16)
plt.ylabel("Count", fontsize=16)
cust = df[df.user_type=='Customer']
ax[1].hist(cust.distance_miles, bins=bins,  color='b', alpha=0.8, edgecolor='k')
plt.sca(ax[1])
plt.xticks(np.arange(0, 4, 0.1))
plt.title("Customers", fontsize=16)
plt.xlabel("Distance in miles", fontsize=16)
plt.ylabel("Count", fontsize=16)
ax[2].hist(df[df.bike_share_for_all_trip == 'Yes'].distance_miles, bins=bins,  color='b', alpha=0.8, edgecolor='k')
plt.sca(ax[2])
plt.xticks(np.arange(0, 4, 0.1))
plt.title("Bike Share", fontsize=16)
plt.xlabel("Distance in miles", fontsize=16)
plt.ylabel("Count", fontsize=16)
plt.tight_layout()
plt.show()


data = df[df.duration_mins < 20]
ax = sns.catplot(data=data, y='duration_mins', col="user_type", kind='box')
ax.fig.suptitle("Duration in minutes of Rentals for Subscribers and Customers", y=1.05, fontsize=16)
plt.show();


ax = sns.catplot(data=data, y='duration_mins', col="user_type", kind='violin')
ax.fig.suptitle("Duration in minutes of Rentals for Subscribers and Customers", y=1.05, fontsize=16)
plt.show();


## Which station sees the most Bike Share for customers users rentals starting point
a = df[df.user_type == 'Customer'].start_station_name.value_counts()[:40]
sns.barplot(a, a.index, palette='autumn')
sns.set(rc={'figure.figsize':(16, 10)})
plt.yticks(fontsize=16)
plt.title("Rentals Count vs Station for customers", fontsize=16)
plt.xlabel("Rentals Count", fontsize=16)
plt.ylabel("Station", fontsize=16)
plt.tight_layout()
plt.show()


## Which station sees the most Bike Share for subscribers users rentals starting point
a = df[df.user_type == 'Subscriber'].start_station_name.value_counts()[:40]
sns.barplot(a, a.index, palette='autumn')
sns.set(rc={'figure.figsize':(16, 10)})
plt.yticks(fontsize=16)
plt.title("Rentals Count vs Station for subscribers", fontsize=16)
plt.xlabel("Rentals Count", fontsize=16)
plt.ylabel("Station", fontsize=16)
plt.tight_layout()
plt.show()


## Which station sees the most Bike Share for all trip program users rentals starting point
a = df[df.bike_share_for_all_trip == "Yes"].start_station_name.value_counts()[:40]
sns.barplot(a, a.index, palette='autumn')
sns.set(rc={'figure.figsize':(16, 10)})
plt.yticks(fontsize=16)
plt.title("Rentals Count vs Station for bike share", fontsize=16)
plt.xlabel("Rentals Count", fontsize=16)
plt.ylabel("Station", fontsize=16)
plt.tight_layout()
plt.show()


# day and hours rental distribution for subscribers 
a = sns.FacetGrid(df[df.user_type=='Customer'], col='start_day', col_wrap=4, col_order=days, sharey=True)
a = (a.map(plt.hist, 'start_hour', bins=np.arange(0, 24, 1), color='b', alpha=0.8, edgecolor='k')
     .set_axis_labels("Day of the week", "Start Hour"))
a.set(xticks=np.arange(0, 24, 2))
plt.suptitle("Start Hour vs Day of the Week for Subscribers", y=1.1)
plt.show()


# heat map for number of rentals with hour and day of the week
a = df[df.user_type=='Subscriber'].groupby(['start_hour', 'start_day'])['bike_id'].size()
a = a.reset_index().pivot('start_hour', 'start_day', 'bike_id')[days]
heat_map = sns.heatmap(a, cmap = 'viridis_r', annot=True, robust=True, fmt='d', linewidths=.5)
plt.title('Subscriber', y=1)
plt.xlabel('Weekday', labelpad = 18)
plt.ylabel('Start Time Hour',  labelpad = 18)
plt.show()


# new dataframe with the only needed columns for location
df2 = df[['start_station_name', 'start_station_latitude', 'start_station_longitude', 'end_station_name', 
             'end_station_latitude', 'end_station_longitude', 'user_type', 'bike_share_for_all_trip']]


df2.start_station_latitude, df2.start_station_longitude = df2.start_station_latitude.astype(str), df2.start_station_longitude.astype(str)
df2.end_station_latitude, df2.end_station_longitude = df2.end_station_latitude.astype(str), df2.end_station_longitude.astype(str)

/home/abdulrahman/anaconda3/lib/python3.8/site-packages/pandas/core/generic.py:5168: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  self[name] = value


from IPython.display import Image
base_html='maps_html/'
base_imgs='maps_imgs/'


fm = folium.Map(location=[37.8272, -122.2913], tiles='Stamen Terrain', zoom_start=10)
c = df2[df2.user_type == 'Customer'].start_station_latitude.value_counts()[:40].index
test = df2[df2.user_type == 'Customer']
d = test.start_station_longitude.value_counts()[:40].index


def add_bikes_to_map(mp, stations_latitudes, stations_longitude):
    """
    Add red bikes to map with locations' latitude and longitude
    """
    for a, b in zip(c, d):
        pop = df2[df2.start_station_latitude==a].start_station_name.unique()[0]
        tooltip = 'Click me!'
        icon=folium.Icon(color='black', icon='bicycle', icon_color="red", prefix='fa', icon_size=(0, 0))
        folium.Marker(location = [float(a), float(b)], popup=pop, tooltip='click here', icon=icon).add_to(mp)


add_bikes_to_map(fm, c, d)
map_cust_file = 'map_customers.html'
map_cust_img = 'map_customers.png'
fm.save(base_html+map_cust_file)


Image(filename=base_imgs+map_cust_img)


fm = folium.Map(location=[37.8272, -122.2913], tiles='Stamen Terrain', zoom_start=10)
c = df2[df2.user_type == 'Subscriber'].start_station_latitude.value_counts()[:40].index
test = df2[df2.user_type == 'Subscriber']
d = test.start_station_longitude.value_counts()[:40].index


add_bikes_to_map(fm, c, d)
map_subs_file = 'map_subscribers.html'
map_subs_img = 'map_subscribers.png'
fm.save(base_html+map_cust_file)


Image(filename=base_imgs+map_subs_img)


fm = folium.Map(location=[37.8272, -122.2913], tiles='Stamen Terrain', zoom_start=10)
c = df2[df2.bike_share_for_all_trip=='Yes'].start_station_latitude.value_counts()[:40].index
d = df2[df2.bike_share_for_all_trip=='Yes'].start_station_longitude.value_counts()[:40].index


add_bikes_to_map(fm, c, d)
map_bikeshare_file = 'map_bikeshare.html'
map_bikeshare_img = 'map_bikeshare.png'
fm.save(base_html+map_cust_file)


Image(filename=base_imgs+map_bikeshare_img)

	duration_sec	start_time	end_time	start_station_id	start_station_name	start_station_latitude	start_station_longitude	end_station_id	end_station_name	end_station_latitude	end_station_longitude	bike_id	user_type	bike_share_for_all_trip	rental_access_method
0	80825	2019-01-31 17:57:44.6130	2019-02-01 16:24:49.8640	229.0	Foothill Blvd at 42nd Ave	37.775745	-122.213037	196.0	Grand Ave at Perkins St	37.808894	-122.256460	4861	Subscriber	No	NaN
1	65900	2019-01-31 20:58:33.8860	2019-02-01 15:16:54.1730	4.0	Cyril Magnin St at Ellis St	37.785881	-122.408915	134.0	Valencia St at 24th St	37.752428	-122.420628	5506	Subscriber	No	NaN
2	62633	2019-01-31 18:06:52.9240	2019-02-01 11:30:46.5300	245.0	Downtown Berkeley BART	37.870139	-122.268422	157.0	65th St at Hollis St	37.846784	-122.291376	2717	Customer	No	NaN
3	44680	2019-01-31 19:46:09.7190	2019-02-01 08:10:50.3180	85.0	Church St at Duboce Ave	37.770083	-122.429156	53.0	Grove St at Divisadero	37.775946	-122.437777	4557	Customer	No	NaN
4	60709	2019-01-31 14:19:01.5410	2019-02-01 07:10:51.0650	16.0	Steuart St at Market St	37.794130	-122.394430	28.0	The Embarcadero at Bryant St	37.787168	-122.388098	2100	Customer	No	NaN

	duration_sec	start_time	end_time	start_station_id	start_station_name	start_station_latitude	start_station_longitude	end_station_id	end_station_name	end_station_latitude	end_station_longitude	bike_id	user_type	bike_share_for_all_trip	rental_access_method
2009651	542	2019-10-22 08:14:57.8340	2019-10-22 08:23:59.9140	241.0	Ashby BART Station	37.852477	-122.270213	248.0	Telegraph Ave at Ashby Ave	37.855956	-122.259795	849	Customer	No	NaN
1264604	427	2019-07-28 20:13:12.2270	2019-07-28 20:20:19.9980	223.0	16th St Mission BART Station 2	37.764765	-122.420091	336.0	Potrero Ave and Mariposa St	37.763281	-122.407377	66	Subscriber	No	NaN
35143	1077	2019-01-28 09:04:47.5880	2019-01-28 09:22:44.9370	104.0	4th St at 16th St	37.767045	-122.390833	15.0	San Francisco Ferry Building (Harry Bridges Pl...	37.795392	-122.394203	5477	Subscriber	No	NaN
745541	747	2019-04-13 10:13:04.3410	2019-04-13 10:25:32.0900	55.0	Webster St at Grove St	37.777053	-122.429558	54.0	Alamo Square (Steiner St at Fulton St)	37.777547	-122.433274	4960	Customer	No	NaN
959095	612	2019-05-16 10:15:08.9150	2019-05-16 10:25:21.3590	218.0	DeFremery Park	37.812331	-122.285171	235.0	Union St at 10th St	37.807239	-122.289370	3418	Customer	No	NaN

	count	mean	std	min	25%	50%	75%	max
duration_sec	2506983.0	807.648330	1974.713981	60.000000	359.000000	571.000000	887.000000	912110.00
start_station_id	2426249.0	146.504749	122.317102	3.000000	47.000000	105.000000	243.000000	498.00
start_station_latitude	2506983.0	37.765064	0.136370	0.000000	37.769305	37.780526	37.795393	45.51
start_station_longitude	2506983.0	-122.349919	0.308965	-122.514299	-122.413004	-122.398285	-122.291415	0.00
end_station_id	2424081.0	142.704424	121.429649	3.000000	43.000000	101.000000	239.000000	498.00
end_station_latitude	2506983.0	37.764219	0.239289	0.000000	37.770030	37.780760	37.795873	45.51
end_station_longitude	2506983.0	-122.345908	0.708042	-122.514287	-122.411726	-122.398113	-122.293400	0.00
bike_id	2506983.0	27898.327162	114606.651187	4.000000	1952.000000	4420.000000	9682.000000	999941.00

	duration_sec	start_time	end_time	start_station_id	start_station_name	start_station_latitude	start_station_longitude	end_station_id	end_station_name	end_station_latitude	end_station_longitude	bike_id	user_type	bike_share_for_all_trip
1881476	714	2019-09-09 07:25:39.0460	2019-09-09 07:37:33.2520	163.0	Lake Merritt BART Station	37.797320	-122.265320	212.0	Mosswood Park	37.824893	-122.260437	3385	Subscriber	No
1633394	2043	2019-08-13 12:19:34.5150	2019-08-13 12:53:37.9700	343.0	Bryant St at 2nd St	37.783172	-122.393572	6.0	The Embarcadero at Sansome St	37.804770	-122.403234	9513	Subscriber	No
773735	513	2019-04-10 18:38:32.5680	2019-04-10 18:47:06.3580	364.0	China Basin St at 3rd St	37.772000	-122.389970	16.0	Steuart St at Market St	37.794130	-122.394430	7013	Subscriber	No
182963	843	2019-01-03 08:15:31.0790	2019-01-03 08:29:34.9960	193.0	Grand Ave at Santa Clara Ave	37.812744	-122.247215	182.0	19th Street BART Station	37.809013	-122.268247	890	Subscriber	No
1066543	518	2019-06-28 09:03:56.1590	2019-06-28 09:12:34.6810	24.0	Spear St at Folsom St	37.789677	-122.390428	284.0	Yerba Buena Center for the Arts (Howard St at ...	37.784872	-122.400876	2819	Subscriber	No

	duration_sec	start_time	end_time	start_station_id	start_station_name	start_station_latitude	start_station_longitude	end_station_id	end_station_name	end_station_latitude	end_station_longitude	bike_id	user_type	bike_share_for_all_trip
740368	685	2019-04-13 17:58:08.2260	2019-04-13 18:09:33.5790	239.0	Bancroft Way at Telegraph Ave	37.868813	-122.258764	175.0	49th St at Telegraph Ave	37.835946	-122.262366	5450	Subscriber	No
177447	275	2019-01-04 01:33:21.4660	2019-01-04 01:37:56.7150	15.0	San Francisco Ferry Building (Harry Bridges Pl...	37.795392	-122.394203	10.0	Washington St at Kearny St	37.795393	-122.404770	4417	Subscriber	Yes
2353773	1137	2019-11-01 08:46:45.3140	2019-11-01 09:05:43.0750	76.0	McCoppin St at Valencia St	37.771662	-122.422423	24.0	Spear St at Folsom St	37.789677	-122.390428	13023	Customer	No
762469	214	2019-04-11 18:01:31.0220	2019-04-11 18:05:05.9090	104.0	4th St at 16th St	37.767045	-122.390833	81.0	Berry St at 4th St	37.775880	-122.393170	6328	Subscriber	No
2014845	146	2019-10-21 16:29:25.1190	2019-10-21 16:31:51.8240	8.0	The Embarcadero at Vallejo St	37.799953	-122.398525	16.0	Steuart St at Market St	37.794130	-122.394430	9682	Subscriber	No

Ford Go Bike Communication¶

Preliminary Wrangling¶

Loading the dataset¶

Cleaning¶

Dataset structure¶

What is the structure of your dataset?¶

What is/are the main feature(s) of interest in your dataset?¶

What features in the dataset do you think will help support your investigation into your feature(s) of interest?¶

Univariate Exploration¶

Distribution of Rental duration in minutes¶

Distribution of Customer vs Subscribers¶

Day, Month and Hour vs Rentals¶

Distance travelled by Subscribers and Customers¶

Percentage of Rental duration for Subscribers and Customers¶

Bivariate Exploration¶

Distribution of rental duration in minutes (subscribers)¶

Distribution of rental duration in minutes (customers)¶

Distribution of rental duration in minutes (all users)¶

Distance travelled in miles by Subscribers¶

Duration in minutes of Rentals for Subscribers and Customers¶

Stations with the most customers rentals¶

Stations with the most subscribers rentals¶

Multivariate Exploration¶

Distribution of Start Day and Start Hour for Customers¶

Heat map of Time vs Subscribers Rentals.¶

Locations¶

Top 40 locations of rentals for Customers¶

Top 40 locations of rentals for Subscribers¶

Talk about some of the relationships you observed in this part of the investigation. Were there features that strengthened each other in terms of looking at your feature(s) of interest?¶

Were there any interesting or surprising interactions between features?¶

Summary¶

	duration_mins	start_day	end_day	start_month	end_month	start_hour	end_hour	duration_sec	start_time	end_time	...	start_station_name	start_station_latitude	start_station_longitude	end_station_id	end_station_name	end_station_latitude	end_station_longitude	bike_id	user_type	bike_share_for_all_trip
0	1347.083333	Thu	Fri	Jan	Feb	17	16	80825	2019-01-31 17:57:44.613	2019-02-01 16:24:49.864	...	Foothill Blvd at 42nd Ave	37.775745	-122.213037	196.0	Grand Ave at Perkins St	37.808894	-122.256460	4861	Subscriber	No
1	1098.333333	Thu	Fri	Jan	Feb	20	15	65900	2019-01-31 20:58:33.886	2019-02-01 15:16:54.173	...	Cyril Magnin St at Ellis St	37.785881	-122.408915	134.0	Valencia St at 24th St	37.752428	-122.420628	5506	Subscriber	No
2	1043.883333	Thu	Fri	Jan	Feb	18	11	62633	2019-01-31 18:06:52.924	2019-02-01 11:30:46.530	...	Downtown Berkeley BART	37.870139	-122.268422	157.0	65th St at Hollis St	37.846784	-122.291376	2717	Customer	No
3	744.666667	Thu	Fri	Jan	Feb	19	8	44680	2019-01-31 19:46:09.719	2019-02-01 08:10:50.318	...	Church St at Duboce Ave	37.770083	-122.429156	53.0	Grove St at Divisadero	37.775946	-122.437777	4557	Customer	No
4	1011.816667	Thu	Fri	Jan	Feb	14	7	60709	2019-01-31 14:19:01.541	2019-02-01 07:10:51.065	...	Steuart St at Market St	37.794130	-122.394430	28.0	The Embarcadero at Bryant St	37.787168	-122.388098	2100	Customer	No

	duration_mins	start_day	end_day	start_month	end_month	start_hour	end_hour	duration_sec	start_time	end_time	...	start_station_latitude	start_station_longitude	end_station_id	end_station_name	end_station_latitude	end_station_longitude	bike_id	user_type	bike_share_for_all_trip	distance_miles
1590111	10.666667	Mon	Mon	Aug	Aug	18	18	640	2019-08-19 18:21:07.650	2019-08-19 18:31:48.373	...	37.786928	-122.398113	5.0	Powell St BART Station (Market St at 5th St)	37.783899	-122.408445	2739	Subscriber	No	0.601738
1519803	10.250000	Thu	Thu	Aug	Aug	9	9	615	2019-08-29 09:10:36.692	2019-08-29 09:20:52.591	...	37.776639	-122.395526	58.0	Market St at 10th St	37.776619	-122.417385	10004	Subscriber	No	1.193742
1948355	22.650000	Tue	Tue	Oct	Oct	22	22	1359	2019-10-29 22:21:26.406	2019-10-29 22:44:05.511	...	37.772301	-122.393028	373.0	Potrero del Sol Park (25th St at Utah St)	37.751792	-122.405216	10958	Customer	No	1.565628
982704	5.316667	Sun	Sun	May	May	3	3	319	2019-05-12 03:42:19.440	2019-05-12 03:47:39.266	...	37.755213	-122.420975	107.0	17th St at Dolores St	37.763015	-122.426497	218	Subscriber	No	0.617745
2284853	9.366667	Mon	Mon	Nov	Nov	14	14	562	2019-11-11 14:37:51.553	2019-11-11 14:47:14.082	...	37.337122	-121.883215	304.0	Jackson St at 5th St	37.348759	-121.894798	2028	Subscriber	No	1.025299

	duration_mins	start_day	end_day	start_month	end_month	start_hour	end_hour	start_station_id	start_station_name	start_station_latitude	start_station_longitude	end_station_id	end_station_name	end_station_latitude	end_station_longitude	bike_id	user_type	bike_share_for_all_trip	distance_miles
815501	2	Sat	Sat	Apr	Apr	18	18	60.0	8th St at Ringold St	37.774520	-122.409449	350.0	8th St at Brannan St	37.771431	-122.405787	5380	Subscriber	No	0.292514
154018	17	Wed	Wed	Jan	Jan	6	6	144.0	Precita Park	37.747300	-122.411403	363.0	Salesforce Transit Center (Natoma St at 2nd St)	37.787492	-122.398285	4554	Subscriber	No	2.867976
1733141	24	Fri	Fri	Sep	Sep	17	17	258.0	University Ave at Oxford St	37.872355	-122.266447	156.0	Stanford Ave at Hollis St	37.838443	-122.288665	11991	Subscriber	No	2.638029
988909	5	Fri	Fri	May	May	17	17	169.0	Bushrod Park	37.846516	-122.265304	241.0	Ashby BART Station	37.852477	-122.270213	2849	Subscriber	No	0.491284
18146	12	Wed	Wed	Jan	Jan	7	7	349.0	Howard St at Mary St	37.781010	-122.405666	81.0	Berry St at 4th St	37.775880	-122.393170	2609	Customer	No	0.768969

Ford Go Bike Communication¶

Preliminary Wrangling¶

Loading the dataset¶

Cleaning¶

Dataset structure¶

What is the structure of your dataset?¶

What is/are the main feature(s) of interest in your dataset?¶

What features in the dataset do you think will help support your investigation into your feature(s) of interest?¶

Univariate Exploration¶

Distribution of Rental duration in minutes¶

Distribution of Customer vs Subscribers¶

Day, Month and Hour vs Rentals¶

How many enrolled in bike sharing scheme ?¶

Distance travelled by Subscribers and Customers¶

Percentage of Rental duration for Subscribers and Customers¶

Bivariate Exploration¶

Distribution of rental duration in minutes (subscribers)¶

Distribution of rental duration in minutes (customers)¶

Distribution of rental duration in minutes (all users)¶

Distance travelled in miles by Subscribers¶

Duration in minutes of Rentals for Subscribers and Customers¶

Stations with the most customers rentals¶

Stations with the most subscribers rentals¶

Stations with the most bike share rentals¶

Multivariate Exploration¶

Distribution of Start Day and Start Hour for Customers¶

Heat map of Time vs Subscribers Rentals.¶

Locations¶

Top 40 locations of rentals for Customers¶

Top 40 locations of rentals for Subscribers¶

Top 40 locations of rentals for Bike Share for all users¶

Talk about some of the relationships you observed in this part of the investigation. Were there features that strengthened each other in terms of looking at your feature(s) of interest?¶

Were there any interesting or surprising interactions between features?¶

Summary¶